© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 72751
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding assisted suicide and euthanasia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conti
    -0.06
     themselves
    -0.06
    abay
    -0.06
     contemporary
    -0.06
     Ske
    -0.06
    datal
    -0.06
    rame
    -0.06
    rire
    -0.06
    ayer
    -0.06
    ries
    -0.06
    POSITIVE LOGITS
     quit
    0.08
     his
    0.07
     Guinness
    0.07
    妻
    0.07
    Ðĭ
    0.07
    ulfilled
    0.07
    /*č↵
    0.07
    ADX
    0.07
    .visitMethod
    0.07
    REDENTIAL
    0.06
    Activations Density 0.022%

    No Known Activations